Senior AI Applications Engineer — Production LLMs

PharmaEssentia U.S.A.; Burlington (MA); Hybrid; USD 140,000 - 182,000; Full time

Benefits offered by this job

Comprehensive medical coverage

Dental and vision coverage

Generous paid time‑off

401(k) retirement plan

Medical & Dependent Care FSA

Cell phone reimbursement

Employee Assistance Program

Free parking

Job summary

PharmaEssentia USA seeks a Senior Engineer, AI Applications in Burlington, MA, to build production AI tools that turn governed data into field-ready assets. You will deliver LLM‑based applications, orchestrate retrievals, and ensure measurable performance in collaboration with GDAI.

You will work hybrid, three days on-site weekly, with a strong emphasis on secure, scalable deployments and close partnership with Data Product Engineering and AI Strategy teams.

Qualifications

• Bachelor’s degree required; technical degree preferred.
• 5+ years building production software with hands‑on AI/LLM apps.
• Strong Python and SQL; experience with cloud data warehouses (Snowflake).
• Experience with retrieval, context management, tool and API integration, and agent orchestration.
• Experience deploying services in the cloud with observability and incident response.

Responsibilities

• Build agentic and LLM‑based applications against Snowflake data assets; from MVP to production.
• Implement retrieval, orchestration, evaluation, and monitoring for measurable performance.
• Deliver early high‑value use cases with real users; iterate with feedback.
• Integrate AI services with field systems so outputs appear in existing workflows.

Skills

Python

SQL

LLM‑based development

Agent orchestration

Cloud deployment

Education

Bachelor’s degree in computer science or related field

Tools

Snowflake

APIs integration

CRM integration (Veeva/Salesforce)

Observability tools

Job description

PharmaEssentia USA seeks a Senior Engineer, AI Applications in Burlington, MA, to build production AI tools that turn governed data into field-ready assets. You will deliver LLM‑based applications, orchestrate retrievals, and ensure measurable performance in collaboration with GDAI.

You will work hybrid, three days on-site weekly, with a strong emphasis on secure, scalable deployments and close partnership with Data Product Engineering and AI Strategy teams.